{"id":"https://openalex.org/W4412887971","doi":"https://doi.org/10.18653/v1/2025.findings-acl.828","title":"SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation","display_name":"SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887971","doi":"https://doi.org/10.18653/v1/2025.findings-acl.828"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.828","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.828","pdf_url":"https://aclanthology.org/2025.findings-acl.828.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.828.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003447928","display_name":"Ting Xu","orcid":"https://orcid.org/0000-0001-6123-9814"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101547686","display_name":"Zhichao Huang","orcid":"https://orcid.org/0000-0002-7662-5184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhichao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424688","display_name":"Jiankai Sun","orcid":"https://orcid.org/0000-0001-5633-1739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiankai Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046413480","display_name":"Shanbo Cheng","orcid":"https://orcid.org/0000-0002-6115-9483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanbo Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111426224","display_name":"Wai Lam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87750839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"16107","last_page":"16123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9657999873161316,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6918384432792664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6815961599349976},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5215332508087158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3711787164211273},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33288177847862244},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15842720866203308},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06708693504333496}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6918384432792664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6815961599349976},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5215332508087158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3711787164211273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33288177847862244},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15842720866203308},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06708693504333496},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.828","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.828","pdf_url":"https://aclanthology.org/2025.findings-acl.828.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.828","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.828","pdf_url":"https://aclanthology.org/2025.findings-acl.828.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887971.pdf","grobid_xml":"https://content.openalex.org/works/W4412887971.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3011059803","https://openalex.org/W4396701345","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"We":[0],"present":[1],"Sequential":[2],"Policy":[3],"Optimization":[4],"for":[5,94],"Simultaneous":[6],"Machine":[7],"Translation":[8],"(SeqPO-SiMT),":[9],"a":[10,24,30,83],"new":[11],"policy":[12],"optimization":[13],"framework":[14,70],"that":[15,103],"defines":[16],"the":[17,65,72,79,117,129,135,149,159],"simultaneous":[18],"machine":[19],"translation":[20,35,109,161],"(SiMT)":[21],"task":[22],"as":[23,51],"sequential":[25],"decision":[26],"making":[27],"problem,":[28],"incorporating":[29],"tailored":[31,84],"reward":[32],"to":[33,41,75],"enhance":[34],"quality":[36,110],"while":[37,127],"reducing":[38,128],"latency.In":[39,113],"contrast":[40],"popular":[42],"Reinforcement":[43],"Learning":[44],"from":[45,91],"Human":[46],"Feedback":[47],"(RLHF)":[48],"methods,":[49],"such":[50],"PPO":[52],"and":[53,77,97,167],"DPO,":[54],"which":[55],"are":[56],"typically":[57],"applied":[58],"in":[59,125,134],"single-step":[60],"tasks,":[61,101],"SeqPO-SiMT":[62,104,115,153],"effectively":[63],"tackles":[64],"multi-step":[66],"SiMT":[67,73,80,100,140,150],"task.This":[68],"intuitive":[69],"allows":[71],"LLMs":[74],"simulate":[76],"refine":[78],"process":[81],"using":[82],"reward.We":[85],"conduct":[86],"experiments":[87],"on":[88,154],"six":[89],"datasets":[90],"diverse":[92],"domains":[93],"En":[95,99,137],"Zh":[96,98,138],"demonstrating":[102],"consistently":[105],"achieves":[106],"significantly":[107],"higher":[108],"with":[111,142],"lower":[112],"particular,":[114],"outperforms":[116],"supervised":[118],"fine-tuning":[119],"(SFT)":[120],"model":[121],"by":[122,132],"1.13":[123],"points":[124],"COMET,":[126],"Average":[130],"Lagging":[131],"6.17":[133],"NEWSTEST2021":[136],"dataset.While":[139],"operates":[141],"far":[143],"less":[144],"context":[145],"than":[146],"offline":[147,160],"translation,":[148],"results":[151],"of":[152,162],"7B":[155],"LLM":[156],"surprisingly":[157],"rival":[158],"high-performing":[163],"LLMs,":[164],"including":[165],"Qwen-2.5-7B-Instruct":[166],"LLaMA-3-8B-Instruct.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}